def exposure_model(self, model, custom_model=None, bound=False, print_results=True):
r"""Specify the propensity score / inverse probability weight model. Model used to predict the exposure via a
logistic regression model. This model estimates
.. math::
\widehat{\Pr}(A=1|L) = logit^{-1}(\widehat{\beta_0} + \widehat{\beta} L)
Parameters
----------
model : str
Independent variables to predict the exposure. For example, 'var1 + var2 + var3'
custom_model : optional
Input for a custom model that is used in place of the logit model (default). The model must have the
"fit()" and "predict()" attributes. SciKit-Learn style models supported as custom models. In the
background, AIPTW will fit the custom model and generate the predicted probablities
bound : float, list, optional
Value between 0,1 to truncate predicted probabilities. Helps to avoid near positivity violations.
Specifying this argument can improve finite sample performance for random positivity violations. However,
truncating weights leads to additional confounding. Default is False, meaning no truncation of
predicted probabilities occurs. Providing a single float assumes symmetric trunctation, where values below
or above the threshold are set to the threshold value. Alternatively a list of floats can be provided for
asymmetric trunctation, with the first value being the lower bound and the second being the upper bound
print_results : bool, optional
Whether to print the fitted model results. Default is True (prints results)
"""
self.__mweight = model
self._exp_model = self.exposure + ' ~ ' + model
if custom_model is None:
d, n, iptw = iptw_calculator(df=self.df, treatment=self.exposure, model_denom=model, model_numer='1',
weight=self._weight_, stabilized=False, standardize='population',
bound=None, print_results=print_results)
else:
self._exp_model_custom = True
data = patsy.dmatrix(model + ' - 1', self.df)
d = exposure_machine_learner(xdata=np.asarray(data),
ydata=np.asarray(self.df[self.exposure]),
ml_model=copy.deepcopy(custom_model),
print_results=print_results)
g1w = d
g0w = 1 - d
# Applying bounds AFTER extracting g1 and g0
if bound:
g1w = probability_bounds(g1w, bounds=bound)
g0w = probability_bounds(g0w, bounds=bound)
self.df['_g1_'] = g1w
self.df['_g0_'] = g0w
self._fit_exposure_ = True
def treatment_model(self,
model_denominator,
model_numerator='1',
stabilized=True,
bound=False,
print_results=True):
"""Logistic regression model(s) for propensity score models. The model denominator must be specified for both
stabilized and unstabilized weights. The optional argument 'model_numerator' allows specification of the
stabilization factor for the weight numerator. By default model results are returned
Parameters
------------
model_denominator : str
String listing variables to predict the exposure via `patsy` syntax. For example, `'var1 + var2 + var3'`.
This is for the predicted probabilities of the denominator
model_numerator : str, optional
Optional string listing variables to predict the exposure, separated by +. Only used to calculate the
numerator. Default ('1') calculates the overall probability of exposure. In general this is recommended. If
confounding variables are included in the numerator, they would later need to be adjusted for in the faux
marginal structural argument. Additionally, used for assessment of effect measure modification. Argument is
also only used when calculating stabilized weights
stabilized : bool, optional
Whether to return stabilized or unstabilized weights. Default is stabilized weights (True)
bound : float, list, optional
Value between 0,1 to truncate predicted probabilities. Helps to avoid near positivity violations.
Specifying this argument can improve finite sample performance for random positivity violations. However,
inference becomes limited to the restricted population. Default is False, meaning no truncation of
predicted probabilities occurs. Providing a single float assumes symmetric trunctation. A collection of
floats can be provided for asymmetric trunctation
print_results : bool, optional
Whether to print the model results from the regression models. Default is True
"""
# Calculating denominator probabilities
self.__mdenom = model_denominator
self.df['__denom__'], self.df[
'__numer__'], self.iptw = iptw_calculator(
df=self.df,
treatment=self.treatment,
model_denom=model_denominator,
model_numer=model_numerator,
weight=self._weight_,
stabilized=stabilized,
standardize=self.standardize,
bound=bound,
print_results=print_results)
def exposure_model(self, model, bound=False, print_results=True):
r"""Specify the propensity score / inverse probability weight model. Model used to predict the exposure via a
logistic regression model. This model estimates
.. math::
\widehat{\Pr}(A=1|L) = logit^{-1}(\widehat{\beta_0} + \widehat{\beta} L)
Parameters
----------
model : str
Independent variables to predict the exposure. For example, 'var1 + var2 + var3'
bound : float, list, optional
Value between 0,1 to truncate predicted probabilities. Helps to avoid near positivity violations.
Specifying this argument can improve finite sample performance for random positivity violations. However,
truncating weights leads to additional confounding. Default is False, meaning no truncation of
predicted probabilities occurs. Providing a single float assumes symmetric trunctation, where values below
or above the threshold are set to the threshold value. Alternatively a list of floats can be provided for
asymmetric trunctation, with the first value being the lower bound and the second being the upper bound
print_results : bool, optional
Whether to print the fitted model results. Default is True (prints results)
"""
self.__mweight = model
self._exp_model = self.exposure + ' ~ ' + model
d, n, iptw = iptw_calculator(df=self.df,
treatment=self.exposure,
model_denom=model,
model_numer='1',
weight=self._weight_,
stabilized=False,
standardize='population',
bound=None,
print_results=print_results)
self.df['_g1_'] = d
self.df['_g0_'] = 1 - d
# Applying bounds AFTER extracting g1 and g0
if bound:
self.df['_g1_'] = _bounding_(self.df['_g1_'], bounds=bound)
self.df['_g0_'] = _bounding_(self.df['_g0_'], bounds=bound)
self._fit_exposure_ = True
def treatment_model(self,
model_denominator,
model_numerator='1',
bound=None,
stabilized=True,
print_results=False):
"""Logistic regression model(s) for estimating inverse probability of treatment weights (IPTW). The model
denominator must be specified for both stabilized and unstabilized weights. The optional argument
'model_numerator' allows specification of the stabilization factor for the weight numerator. By default model
results are returned
Parameters
----------
model_denominator : str
String listing variables to predict the exposure, separated by +. For example, 'var1 + var2 + var3'. This
is for the predicted probabilities of the denominator
model_numerator : str, optional
Optional string listing variables to predict the selection separated by +. Only used to calculate the
numerator. Default ('1') calculates the overall probability of selection. In general, this is recommended.
Adding in other variables means they are no longer accounted for in estimation of IPSW. Argument is also
only used when calculating stabilized weights
bound : float, list, optional
Value between 0,1 to truncate predicted probabilities. Helps to avoid near positivity violations.
Specifying this argument can improve finite sample performance for random positivity violations. However,
inference becomes limited to the restricted population. Default is False, meaning no truncation of
predicted probabilities occurs. Providing a single float assumes symmetric trunctation. A collection of
floats can be provided for asymmetric trunctation
stabilized : bool, optional
Whether to generated stabilized IPTW. Default is True, which returns the stabilized IPTW
print_results : bool, optional
Whether to print the model results from the regression models. Default is True
"""
d, n, self.iptw = iptw_calculator(df=self.df,
treatment=self.exposure,
model_denom=model_denominator,
model_numer=model_numerator,
weight=self.weight,
stabilized=stabilized,
standardize='population',
bound=bound,
print_results=print_results)